{"id":"W2951497968","doi":"","title":"A new tool for multi-block PLS discriminant analysis of metabolomic data: application to systems epidemiology","year":2019,"lang":"en","type":"preprint","venue":"Prodinra (INRA Bordeaux-Aquitaine)","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"Association Nationale de la Recherche et de la Technologie; Agence Nationale de la Recherche","keywords":"Computer science; Linear discriminant analysis; Metabolomics; Data mining; Nutritional epidemiology; Partial least squares regression; Metadata; Machine learning; Artificial intelligence; Bioinformatics; Biology; Epidemiology; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006317594,0.002525483,0.001420189,0.00305167,0.0005524607,0.001879059,0.001574072,0.001169161,0.01565687],"category_scores_gemma":[0.01803578,0.000994994,0.003291967,0.002290763,0.0005866946,0.0015716,0.003094816,0.002576077,0.006604691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004744984,"about_ca_system_score_gemma":0.001713288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002163033,"about_ca_topic_score_gemma":0.00206533,"domain_scores_codex":[0.9973609,0.001360231,0.0002083533,0.0004914013,0.0004820873,0.00009707585],"domain_scores_gemma":[0.9936303,0.004606415,0.0004079384,0.0005699355,0.0006638123,0.0001215614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009139045,0.0004757966,0.01139081,0.002506034,0.002212941,0.0006798262,0.0009162712,0.09014251,0.02072702,0.03839344,0.04798584,0.7836556],"study_design_scores_gemma":[0.0002169583,0.0003055931,0.008956434,0.0002804301,0.0003390269,0.0007321352,0.000155732,0.8117423,0.01296661,0.05222171,0.1118223,0.000260795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001484289,0.0001462688,0.9852811,0.0001083691,0.00005304825,0.00006603474,0.00125909,0.01124525,0.0003566132],"genre_scores_gemma":[0.02938063,0.0002919281,0.9622273,0.000154244,0.00007291587,0.0006980328,0.002702153,0.003075316,0.001397526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01565687,"threshold_uncertainty_score":0.0523774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08087452289367117,"score_gpt":0.3721249244209328,"score_spread":0.2912504015272616,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}